In this article, we propose a novel spectral tensor layer for communication-free distributed deep learning. The overall framework is as follows: first, we represent the data in tensor form (instead of ...

Spatial accelerator is a specialized hardware to provide noticeable performance speedup for tensor computations. It also brings a challenge to map tensor computations on spatial accelerators.

Resistant hypertension (RH) is defined as above-goal elevated blood pressure (BP) in a patient despite the concurrent use of 3 antihypertensive drug classes, commonly including a long-acting calcium ...

Anisotropy in low-dimensional materials offers an extra degree of freedom to understand and tune the peculiar or potential properties to design novel electronic, optical, thermal, and optoelectronic ...

GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.

We investigate a novel approach to approximate tensor-network contraction via the exact, matrix-free decomposition of full tensor-networks. We study this method as a means to eliminate the propagat ...

To fully harness the power of LUT-based mpGEMM, we introduce LUT Tensor Core, a software-hardware co-design optimized for low-bit LLM inference. Specifically, we introduce software-based operator ...